src/Crypto/chacha_u4.h


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155.highlight .hll { background-color: #ffffcc }
.highlight .c { color: #888888 } /* Comment */
.highlight .err { color: #a61717; background-color: #e3d2d2 } /* Error */
.highlight .k { color: #008800; font-weight: bold } /* Keyword */
.highlight .ch { color: #888888 } /* Comment.Hashbang */
.highlight .cm { color: #888888 } /* Comment.Multiline */
.highlight .cp { color: #cc0000; font-weight: bold } /* Comment.Preproc */
.highlight .cpf { color: #888888 } /* Comment.PreprocFile */
.highlight .c1 { color: #888888 } /* Comment.Single */
.highlight .cs { color: #cc0000; font-weight: bold; background-color: #fff0f0 } /* Comment.Special */
.highlight .gd { color: #000000; background-color: #ffdddd } /* Generic.Deleted */
.highlight .ge { font-style: italic } /* Generic.Emph */
.highlight .gr { color: #aa0000 } /* Generic.Error */
.highlight .gh { color: #333333 } /* Generic.Heading */
.highlight .gi { color: #000000; background-color: #ddffdd } /* Generic.Inserted */
.highlight .go { color: #888888 } /* Generic.Output */
.highlight .gp { color: #555555 } /* Generic.Prompt */
.highlight .gs { font-weight: bold } /* /*
u4.h version $Date: 2014/11/11 10:46:58 $
D. J. Bernstein
Romain Dolbeau
Public domain.
*/

// Modified by kerukuro for use in cppcrypto.

#define VEC4_ROT(a,imm) _mm_or_si128(_mm_slli_epi32(a,imm),_mm_srli_epi32(a,(32-imm)))

/* same, but replace 2 of the shift/shift/or "rotation" by byte shuffles (8 & 16) (better) */
#define VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)                                \
   x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot16); \
   x_##c = _mm_add_epi32(x_##c, x_##d); t_##c = _mm_xor_si128(x_##b, x_##c); x_##b = VEC4_ROT(t_##c, 12); \
   x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot8); \
   x_##c = _mm_add_epi32(x_##c, x_##d); t_##c = _mm_xor_si128(x_##b, x_##c); x_##b = VEC4_ROT(t_##c,  7)

#define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)


//  if (!bytes) return;
if (bytes>=256) {
  /* constant for shuffling bytes (replacing multiple-of-8 rotates) */
  __m128i rot16 = _mm_set_epi8(13,12,15,14,9,8,11,10,5,4,7,6,1,0,3,2);
  __m128i rot8  = _mm_set_epi8(14,13,12,15,10,9,8,11,6,5,4,7,2,1,0,3);
  uint32 in12, in13;
  __m128i x_0 = _mm_set1_epi32(x[0]);
  __m128i x_1 = _mm_set1_epi32(x[1]);
  __m128i x_2 = _mm_set1_epi32(x[2]);
  __m128i x_3 = _mm_set1_epi32(x[3]);
  __m128i x_4 = _mm_set1_epi32(x[4]);
  __m128i x_5 = _mm_set1_epi32(x[5]);
  __m128i x_6 = _mm_set1_epi32(x[6]);
  __m128i x_7 = _mm_set1_epi32(x[7]);
  __m128i x_8 = _mm_set1_epi32(x[8]);
  __m128i x_9 = _mm_set1_epi32(x[9]);
  __m128i x_10 = _mm_set1_epi32(x[10]);
  __m128i x_11 = _mm_set1_epi32(x[11]);
  __m128i x_12;// = _mm_set1_epi32(x[12]); /* useless */
  __m128i x_13;// = _mm_set1_epi32(x[13]); /* useless */
  __m128i x_14 = _mm_set1_epi32(x[14]);
  __m128i x_15 = _mm_set1_epi32(x[15]);
  __m128i orig0 = x_0;
  __m128i orig1 = x_1;
  __m128i orig2 = x_2;
  __m128i orig3 = x_3;
  __m128i orig4 = x_4;
  __m128i orig5 = x_5;
  __m128i orig6 = x_6;
  __m128i orig7 = x_7;
  __m128i orig8 = x_8;
  __m128i orig9 = x_9;
  __m128i orig10 = x_10;
  __m128i orig11 = x_11;
  __m128i orig12;// = x_12; /* useless */
  __m128i orig13;// = x_13; /* useless */
  __m128i orig14 = x_14;
  __m128i orig15 = x_15;
  __m128i t_0;
  __m128i t_1;
  __m128i t_2;
  __m128i t_3;
  __m128i t_4;
  __m128i t_5;
  __m128i t_6;
  __m128i t_7;
  __m128i t_8;
  __m128i t_9;
  __m128i t_10;
  __m128i t_11;
  __m128i t_12;
  __m128i t_13;
  __m128i t_14;
  __m128i t_15;

  while (bytes >= 256) {
    const __m128i addv12 = _mm_set_epi64x(1,0);
    const __m128i addv13 = _mm_set_epi64x(3,2);
    __m128i t12, t13;
	uint64 in1213;

    x_0 = orig0;
    x_1 = orig1;
    x_2 = orig2;
    x_3 = orig3;
    x_4 = orig4;
    x_5 = orig5;
    x_6 = orig6;
    x_7 = orig7;
    x_8 = orig8;
    x_9 = orig9;
    x_10 = orig10;
    x_11 = orig11;
    //x_12 = orig12; /* useless */
    //x_13 = orig13; /* useless */
    x_14 = orig14;
    x_15 = orig15;


    in12 = x[12];